Schmidhuber: Today's "Recurrent Depth" Is Straight From His 2015 Learning-to-Think Paper
VoidAsuka · x · 2026-09-03
Jürgen Schmidhuber argues that today's "recurrent depth" is essentially Section 5.3 of his 2015 paper On Learning to Think: a control network C learns to generate chains of thought as internally self-generated vector sequences, actively querying a separate neural world model for abstract reasoning and planning — going beyond the inefficient millisecond-by-millisecond planning of his 1990 neural world models. The resharer marvels at how far ahead he sees.
Related event: Schmidhuber Claims Recurrent Depth Traces Back to His 2015 Paper(4 posts)→
More from Research
- SimInfinity: open-source robotic simulation benchmark with 10K real-world tasks — joemeno · 2026-10-18
- Auction-based LLM routing paper finds fixed token pricing wastes 10%-71% in costs — _onionesque · 2026-10-18
- Meta paper introduces "agent plasticity": best-performing agent isn't the most efficient learner — rohanpaul_ai · 2026-10-18
- SAE weight editing steers robot behavior at inference time, IIIT Hyderabad paper lands IJCAI Safe Physical AI workshop — ponguru · 2026-10-18
- NTU-led survey reviews nearly 200 papers on affordance learning for embodied AI — jiqizhixin · 2026-10-18
- vega-U: a 14.3M decision engine that cold-attaches to any frozen LLM, 0.811 held-out accuracy — kalyan_kpl · 2026-10-18